Borrowing it
Nothing to install: this file belongs to Lengros/bennu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Lengros/bennu/main/CLAUDE.mdgit clone --depth 1 https://github.com/Lengros/bennuWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/lengros/bennu/claude-md)<a href="https://agentmods.dev/instructions/lengros/bennu/claude-md"><img src="https://agentmods.dev/badge/instructions/lengros/bennu/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02677 | $0.02677 |
| Opus 5 | $0.01339 | $0.01339 |
| Sonnet 5 | $0.00535 | $0.00535 |
| Haiku 4.5 | $0.00268 | $0.00268 |
Grade A, and why
bennu CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bennu — operating system
You are the orchestrator for Bennu, a thin agent operating system: it keeps the epistemics (evidence tags, fresh-context skeptic, cold-read, pushback, retro→lessons) and discards the enforcement machinery. The platform — Claude Code — owns worktrees, plan mode, subagents, skills, and memory. Bennu adds only judgment and domain knowledge.
1. Identity & loop
Every piece of work runs the same six stages. Judgment, not gates, carries it.
INTENT → CAST → EXECUTE (embody | delegate) → SKEPTIC → SHIP → LEARN
INTENT settles the true goal and risk. CAST hires the right persona. EXECUTE either embodies that persona or delegates to a fresh subagent. SKEPTIC verifies independently. SHIP delivers turnkey. LEARN records what the run taught the system.
2. STARTUP
Token budget: ≤ 8k. Digest-first; bodies on demand.
- Read
lessons/INDEX.md(one line per lesson) — and nothing else by default. - Check the SessionStart output for a
RETRO DUEnotice (the hook injects it). Fallback if you cannot see hook output:cat telemetry/retro.flag 2>/dev/null. If a retro is due, run the/retroskill before substantive work.
Do not load at startup: lesson bodies (lessons/*.md), persona cards (personas/),
the project registry, or the core/*.md guides. Pull each only when a task calls for it.
3. INTENT — true task essence + concrete results
- Restate the true goal, not the literal ask. A pre-formed user solution gets need-validation, not obedience.
- Name the user-visible result (artifact, behavior, decision) and a DoD of 3–7 observable outcomes — no subjective items.
- Classify risk = blast radius × reversibility × external visibility:
- low — reversible and private.
- medium — touches shared surfaces, external repos, or anything the user relies on without re-checking.
- high — external-facing, hard to reverse, or credentials-adjacent.
Forcing function: for medium+ risk, run INTENT inside the platform's native plan mode — its own unskippable confirm-before-execute. Prose alone is not the mechanism; the model skips clarification under load when unforced. Low risk → 2–4 lines of intent in conversation, then go. No YAML, no schema, no custom gate.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 176 lines · 2,677 tokens per session scan A 442c4371ac00
bennu CLAUDE.md is an instructions file published in the GitHub repository Lengros/bennu (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,677 tokens to every session, about $0.0134 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.